Especificação e implementação de um algoritmo genético para otimização de projetos de iluminação pública

Abstract

The development of public lighting projects in Brazil must meet the standards established in Brazilian standards. Many of these projects is developed through the use of knowledge about "practical rules" practiced by the designers of this area. In some cases are also used computational tools offered, generally, by leading manufacturers of lamps/luminaires. These tools have served only as calculation tools, with some limitations, such as: are not able to verify compliance or not the parameters established by Brazilian standards, most of the luminaires offered in your database are not sold in Brazil, not have no concern about the analysis of the implementation costs of elaborate designs and, finally, present an enormous difficulty in performing tests on a large volume of possible projects. It is the goal of this thesis to develop a methodology and a computational tool for the development of public lighting projects based on genetic algorithm techniques that not only perform the calculations of these projects, but can also test several possible projects using in your database the luminaires marketed in Brazil, providing the user, as a solution, a set of projects that meet the Brazilian standards and classified according the implementation costs of each project. To adjust the proposed algorithm the following performance parameters were modified: number of individuals in the initial population; probability of achievement of the cross-over; probability of achievement of the mutation. A comparison of this method with the projects developed with the use of "practical rules" is performed for various types of existing roads. The results obtained using the proposed methodology and the developed computational tool show that the methodology, including the adjustments in performance parameters, is able to meet the objectives of the work.